© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 37159
    Prev
    Next
    INDEX
    Explanations

    statements about personal accountability or responsibility in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.01
    2:0.08
    3:0.08
    4:0.39
    5:0.02
    6:0.06
    7:0.13
    8:0.03
    9:0.03
    10:0.03
    11:0.05
    Negative Logits
    undai
    -1.49
     Sabha
    -1.45
     subsequent
    -1.40
    MRI
    -1.40
     subsequently
    -1.38
    osponsors
    -1.29
     regularly
    -1.24
    activate
    -1.24
    try
    -1.23
    ivably
    -1.23
    POSITIVE LOGITS
     uniqueness
    1.59
     individuality
    1.46
     vanishing
    1.41
     Quantity
    1.41
     rather
    1.34
     spont
    1.33
     specificity
    1.32
     excellence
    1.29
     heterogeneity
    1.28
    BILITY
    1.27
    Activations Density 0.033%

    No Known Activations